Preprint
Aug 2026
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
This work introduces CamChoreo, a benchmark of 4,229 real single-shot clips with expert-annotated temporal segments, and proposes CamDistill, which distills the same geometric knowledge into lightweight camera tokens during training and removes the 3D model at inference.
Dazhao Du, Shiyan Du, Jian Liu et al.
· 0 citations